AI agents call volt_recommend_route to retrieve information from Volthq without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Model name or partial match to filter offerings (e.g. "llama-70b", "gpt-4o") |
optimize | string | — | What to optimize for (default: balanced) |
min_quality | number | — | Minimum acceptable quality score 0-1 (default: 0.7) |
max_latency_ms | integer | — | Maximum acceptable P95 latency in ms (default: 5000) |
blocked_providers | array | — | Provider IDs to exclude from recommendations |
current_cost_per_million | number | null | — | What you currently pay per million tokens (avg of input+output), for savings estimate |
Parameters from the server's own tool schema.
This tool reads pricing and performance data to provide optimization recommendations. It has no side effects—it does not modify user settings, execute workloads, or commit to any financial obligations. The recommendation is advisory only. While related to cost decisions, it merely retrieves and presents information rather than executing transactions or making binding changes.
From the tool's definition Tool performs information retrieval ('Get the optimal provider recommendation', 'Shows savings') with no mutation of data or execution of external operations.
Attacks that exploit this kind of access
Get the optimal provider recommendation for a model based on cost, latency, reliability, or balanced optimization. Shows savings vs your current cost. It is categorised as a Read tool in the Volthq MCP Server, which means it retrieves data without modifying state.
volt_recommend_route accepts 6 parameters: model, optimize, min_quality, max_latency_ms, blocked_providers, current_cost_per_million. Required: model. The full parameter table on this page comes from the server's own tool schema.
Register the Volthq MCP server in PolicyLayer and add a rule for volt_recommend_route: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Volthq. Nothing to install.
volt_recommend_route is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the volt_recommend_route rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for volt_recommend_route. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
volt_recommend_route is provided by the Volthq MCP server (newageflyfish-max/volthq). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →